1 - 10 of 13 results for: OIT ; Currently searching autumn courses. You can expand your search to include all quarters

This course provides basic skills in quantitative modeling. The objective is to familiarize students with the main steps in an analytical approach to business decision making: constructing an abstract model for a relevant business problem, formulating it in a spreadsheet environment such as Microsoft Excel, and using the tools of optimization, Monte Carlo simulation and sensitivity analysis to generate and interpret recommendations. The class will be taught in a lab style, with short in-class exercises done in small teams, focusing on a variety of applications drawn from online advertising, healthcare, finance, supply chain management, revenue and yield optimization.

The course is aimed at students who already have a background or demonstrated aptitude for quantitative analysis, and thus are comfortable with a more rapid coverage of the topics, in more depth and breadth, than in OIT 245.

This course is an advanced option in the menu of classes satisfying the Core requirement in Optimization and Simulation Modeling (OSM). It is an advanced version of OIT 245 and OIT 247 and it covers a slightly expanded set of concepts pertaining to prescriptive analytics, including static optimization, Monte-Carlo simulation, decision trees and dynamic optimization, and reinforcement learning. The class is taught in an interactive style, focusing on applications drawn from advertising, healthcare, finance, supply chain management, revenue management and pricing, scheduling, and risk management. There are several differences with 245 and 247 that are worth emphasizing. The first difference is in the pace and depth: OIT 248 covers each topic significantly faster and at a deeper level; as such, the class requires slightly more mathematical sophistication (for instance, the ability to quickly digest mathematical formulas and equations). A second difference is that OIT 248 leverages Python instead of Excel for implementation. (We emphasize that OIT 248 uses Python to teach analytics, but is not a course on Python or coding. Although no prior coding experience in Python is required, every student in Advanced is expected to have had some prior coding experience, for instance, through coursework, in their prior jobs, etc.) Lastly, a third difference is that OIT 248 devotes more time to discussing practical issues that arise in real-world, data-driven implementations; so by the end of the course, students should develop a more in-depth mental framework of the topics and leave with a good understanding of how they fit within modern machine-learning / AI pipelines that aid decision-making in complex problems.

Data and Decisions teaches you how to use data and quantitative reasoning to make sound decisions in complex and uncertain environments. The course draws on probability, statistics, and decision theory. Probabilities provide a foundation for understanding uncertainties, such as the risks faced by investors, insurers, and capacity planners. We will discuss the mechanics of probability (manipulating some probabilities to get others) and how to use probabilities to make decisions about uncertain events. Statistics allows managers to use small amounts of information to answer big questions. For example, statistics can help predict whether a new product will succeed or what revenue will be next quarter. The third topic, decision analysis, uses probability and statistics to plan actions, such as whether to test a new drug, buy an option, or explore for oil. In addition to improving your quantitative reasoning skills, this class seeks to prepare you for later classes that draw on this material, including finance, economics, marketing, and operations. At the end we will discuss how this material relates to machine learning and artificial intelligence.

Operations refer to the processes through which businesses produce and deliver products or services. Managing operations well is necessary in order for these processes to be completed in a timely manner, consume minimal resources and costs, and achieve their goal effectively. This course focuses on managerial issues arising in the operations of manufacturing and service industries. The objectives of the course are to introduce operational problems and challenges faced by managers, as well as language, conceptual models, analytical techniques and strategies that are broadly applicable in confronting such problems.

This aim of this course is to cover modern tools for data-driven decision making. Most decision making tasks involve uncertainty that is directly impacted by the amount and complexity of data at hand. Classical decision models rely on strong distributional assumptions about the uncertain events. But in recent years, and due to growing availability of rich data and advances in artificial intelligence (AI), there has been a rapid adoption of AI models that provide more accurate and personalized picture of uncertainty which in turn lead to better decisions. The interplay between the multiple objectives of modeling the data, personalization, and decision optimization has created a number mathematical models that the course aims to cover.

This year-long course takes a hands-on approach to learning about conducting research in Operations, Information and Technology. It will cover a broad spectrum of cutting-edge research in OIT from conceiving an idea to formulating a research problem, deriving results, and publication. The topical content will be customized to the specific interests of the enrolled students, but generally will be concerned with questions of operational interest.

Optimization entails seeking decisions that maximize objectives while satisfying constraints, with applications across engineering, business, economics, statistics, data analysis, and everyday life. This course provides an in-depth and rigorous introduction to mathematical optimization, covering how to formulate, analyze, and solve real-world problems using modern optimization theory and software. Topics include finite-dimensional linear optimization problems with continuous and discrete variables, sensitivity and duality, basic elements of convex analysis, first- and second-order optimality conditions for nonlinear optimization problems, and a discussion of important algorithmic and computational aspects related to optimization. Prerequisites: MATH 113, 115, or equivalent.

This course is offered for students requiring specialized training in an area not covered by existing courses. To register, a student must obtain permission from the faculty member who is willing to supervise the reading.